Self-Compression of Chain-of-Thought via Multi-Agent Reinforcement Learning

TL;DR

This paper introduces a multi-agent reinforcement learning framework called SCMA that reduces redundant reasoning in large models, maintaining accuracy while decreasing inference length by up to 39%.

Contribution

It proposes a novel multi-agent RL approach with specialized agents for segmentation and scoring, effectively balancing brevity and reasoning accuracy.

Findings

Reduces response length by 11.1% to 39.0%.

Boosts reasoning accuracy by 4.33% to 10.02%.

Demonstrates emergent behaviors surpassing vanilla RL.

Abstract

The inference overhead induced by redundant reasoning undermines the interactive experience and severely bottlenecks the deployment of Large Reasoning Models. Existing reinforcement learning (RL)-based solutions tackle this problem by coupling a length penalty with outcome-based rewards. This simplistic reward weighting struggles to reconcile brevity with accuracy, as enforcing brevity may compromise critical reasoning logic. In this work, we address this limitation by proposing a multi-agent RL framework that selectively penalizes redundant chunks, while preserving essential reasoning logic. Our framework, Self-Compression via MARL (SCMA), instantiates redundancy detection and evaluation through two specialized agents: \textbf{a Segmentation Agent} for decomposing the reasoning process into logical chunks, and \textbf{a Scoring Agent} for quantifying the significance of each chunk. The Segmentation and Scoring agents collaboratively define an importance-weighted length penalty during training, incentivizing \textbf{a Reasoning Agent} to prioritize essential logic without introducing inference overhead during deployment. Empirical evaluations across model scales demonstrate that SCMA reduces response length by 11.1\% to 39.0\% while boosting accuracy by 4.33\% to 10.02\%. Furthermore, ablation studies and qualitative analysis validate that the synergistic optimization within the MARL framework fosters emergent behaviors, yielding more powerful LRMs compared to vanilla RL paradigms.